Communications of the ACM
How CDC is Trying to Forecast Coronavirus's Spread
Credit: Carnegie Mellon University
A group of researchers at Carnegie Mellon University (CMU) is one of several dozen teams enlisted by the U.S. Centers for Disease Control (CDC) to adapt their annual flu forecasting techniques to predict the spread of coronavirus.
The CMU team uses three methods for its flu predictions: a “nowcast,” based on recent and historical data from the CDC and other partner organizations, fed into machine learning algorithms to make predictions in real time; another model based on machine learning uses the nowcast and more historical CDC data, and a third crowdsources forecasts. Said CMU’s Roni Rosenfeld, “We're not going to tell you what's going to happen. What we tell you is what are the things that can happen, and how likely is each one of them.”
From Technology Review
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found